MOSS-VL-Realtime is Now Open Source
victormustar · x · 2026-07-14
MosiAI has open-sourced MOSS-VL-Realtime, an 11B vision-language model designed for real-time visual understanding of continuous video streams under the Apache-2.0 license.
It supports asking questions at any point during the video and features a "watch and answer" capability: it can correct or interrupt its answers when the scene changes, and remain silent when evidence is insufficient. The project also offers Base, Instruct, and Realtime versions, supporting bilingual (Chinese and English) multimodal understanding with a context window length of 256K tokens.
Related event: MOSS-VL-Realtime Open-Sourced for Real-time Vision(2 posts)→
More from Multimodal
- Short film 'Odissey of Aeons' made with MiniMax H3 video generation — Musikalandia · 2026-10-27
- Remiqora Video: open-source local studio turns one idea into 4K chained AI videos — inikolax · 2026-10-27
- $5k kale-img-1 fine-tuning contest won with MOSS-Image base, SDXL trails far behind — ostrisai · 2026-10-27
- HN discussion: How far image generation has come since August 2022 — hunterbrooks · 2026-10-27
- FLUX.3 Edit nails a -90° car rotation on first try with just two reference images — EvilBot-666 · 2026-10-27
- Fan-Made AI Series 'Wolverine: Trail of Tears' Episode One Released — ArtificialLightPixel · 2026-10-27